Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification

Simon Chi Lok Yu, Jie He, Victor Basulto, Jeff Pan


Abstract
Hierarchical multi-label text classification (HMTC) aims at utilizing a label hierarchy in multi-label classification. Recent approaches to HMTC deal with the problem of imposing an overconstrained premise on the output space by using contrastive learning on generated samples in a semi-supervised manner to bring text and label embeddings closer. However, the generation of samples tends to introduce noise as it ignores the correlation between similar samples in the same batch. One solution to this issue is supervised contrastive learning, but it remains an underexplored topic in HMTC due to its complex structured labels. To overcome this challenge, we propose **HJCL**, a **H**ierarchy-aware **J**oint Supervised **C**ontrastive **L**earning method that bridges the gap between supervised contrastive learning and HMTC. Specifically, we employ both instance-wise and label-wise contrastive learning techniques and carefully construct batches to fulfill the contrastive learning objective. Extensive experiments on four multi-path HMTC datasets demonstrate that HJCLachieves promising results and the effectiveness of Contrastive Learning on HMTC. Code and data are available at https://github.com/simonucl/HJCL.
Anthology ID:
2023.findings-emnlp.594
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8858–8875
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.594
DOI:
10.18653/v1/2023.findings-emnlp.594
Bibkey:
Cite (ACL):
Simon Chi Lok Yu, Jie He, Victor Basulto, and Jeff Pan. 2023. Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8858–8875, Singapore. Association for Computational Linguistics.
Cite (Informal):
Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification (Yu et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.594.pdf